Deep BI-RADS Network for Improved Cancer Detection from Mammograms
This work addresses breast cancer screening for medical diagnostics, offering an incremental improvement by integrating expert-derived features into deep learning models.
The paper tackled the problem of improving breast cancer detection from mammograms by incorporating textual BI-RADS lesion descriptors with visual data, resulting in substantial performance gains over image-only models on the CBIS-DDSM dataset.
While state-of-the-art models for breast cancer detection leverage multi-view mammograms for enhanced diagnostic accuracy, they often focus solely on visual mammography data. However, radiologists document valuable lesion descriptors that contain additional information that can enhance mammography-based breast cancer screening. A key question is whether deep learning models can benefit from these expert-derived features. To address this question, we introduce a novel multi-modal approach that combines textual BI-RADS lesion descriptors with visual mammogram content. Our method employs iterative attention layers to effectively fuse these different modalities, significantly improving classification performance over image-only models. Experiments on the CBIS-DDSM dataset demonstrate substantial improvements across all metrics, demonstrating the contribution of handcrafted features to end-to-end.